• Home
  • Search
  • Noisy Concurrent Training for Efficient Learning under Label Noise
  • Open Access IconOpen Access
  • Cite Icon23
  • https://doi.org/10.1109/wacv48630.2021.00320Copy DOI Icon

Noisy Concurrent Training for Efficient Learning under Label Noise

  • Jan 1, 2021
  • Fahad Sarfraz +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider learning in isolation, using one-hot encoded labels as the sole source of supervision, and a lack of regularization to discourage memorization as the major shortcomings of the standard training procedure. Thus, we propose Noisy Concurrent Training (NCT) which leverages collaborative learning to use the consensus between two models as an additional source of supervision. Furthermore, inspired by trial-to-trial variability in the brain, we propose a counter-intuitive regularization technique, target variability, which entails randomly changing the labels of a percentage of training samples in each batch as a deterrent to memorization and over-generalization in DNNs. Target variability is applied independently to each model to keep them diverged and avoid the confirmation bias. As DNNs tend to prioritize learning simple patterns first before memorizing the noisy labels, we employ a dynamic learning scheme whereby as the training progresses, the two models increasingly rely more on their consensus. NCT also progressively increases the target variability to avoid memorization in later stages. We demonstrate the effectiveness of our approach on both synthetic and real-world noisy benchmark datasets.

Similar Papers
  • Research Article
  • Citations6

Suppressing label noise in medical image classification using mixup attention and self-supervised learning

  • May 08, 2024
  • Physics in Medicine & Biology
  • Mengdi Gao +5
  • PDF
  • Research Article
  • Citations7

NRN-RSSEG: A Deep Neural Network Model for Combating Label Noise in Semantic Segmentation of Remote Sensing Images

  • Dec 25, 2022
  • Remote Sensing
  • Mengfei Xi +4
  • Research Article
  • Citations12

Exploring Label Probability Sequence to Robustly Learn Deep Convolutional Neural Networks for Road Extraction With Noisy Datasets

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Panle Li +11
  • Research Article
  • Citations4

Towards harnessing feature embedding for robust learning with noisy labels

  • Jun 24, 2022
  • Machine Learning
  • Chuang Zhang +3
  • Research Article
  • Citations358

Image classification with deep learning in the presence of noisy labels: A survey

  • Jan 13, 2021
  • Knowledge-Based Systems
  • Görkem Algan +1
  • Conference Article
  • Citations5

Training Classifiers that are Universally Robust to All Label Noise Levels

  • Jul 18, 2021
  • Jingyi Xu +2
  • Book Chapter
  • Citations4

How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?

  • Jan 01, 2021
  • Bidur Khanal +1
  • Research Article
  • Citations6

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jongwoo Ko +2
  • Research Article

Group benefits instance for data purification

  • Mar 11, 2024
  • Computers and Electrical Engineering
  • Zhenhuang Cai +5
  • Research Article
  • Citations18

A survey on learning from data with label noise via deep neural networks

  • Apr 04, 2025
  • Systems Science & Control Engineering
  • Baoye Song +4
  • Research Article

Alleviating Confirmation Bias in Learning with Noisy Labels via Two-Network Collaboration

  • Mar 11, 2025
  • ACM Transactions on Intelligent Systems and Technology
  • Chenglong Xu +4
  • Research Article
  • Citations21

Dynamics-aware loss for learning with label noise

  • Aug 01, 2023
  • Pattern Recognition
  • Xiu-Chuan Li +5
  • Conference Article
  • Citations2

Making Deep Neural Networks Robust to Label Noise: A Reweighting Loss and Data Filtration

  • Jul 01, 2019
  • Zhengwen Zhang +3
  • Research Article
  • Citations11

A Convergence Path to Deep Learning on Noisy Labels.

  • Apr 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Defu Liu +2
  • Research Article
  • Citations4

Meta-probability Weighting for Improving Reliability of DNNs to Label Noise.

  • Apr 01, 2023
  • IEEE journal of biomedical and health informatics
  • Zhen Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.